Pika Labs just added sound effects to its generative AI videos — here’s how it sounds

Bacon sizzling AI video
(Image credit: Pika Labs)

Pika Labs has added the ability to create sound effects from a text prompt for its generative artificial intelligence videos. 

Now you can make bacon sizzle, lions roar or add footsteps to the video of someone walking down the street.

This is the second audio feature added to the Pika platform, joining a lip sync tool that lets you give characters in AI videos — or action figures — a voice.

Sounds effects are currently only available to subscribers of the Pro plan or above but will likely be rolled out more widely in the coming weeks.

How do Pika Labs sound effects sound?

The sounds are impressive, generated from a simple text prompt they generally mirror what the user requests and, when paired with a video, bring that clip to life.

Creating sound effects from text is a rapidly emerging field, with other tools like MyEdit, AudioCraft and ElevenLabs also offering similar functionality.

I haven't had a chance to try it myself yet but the example videos from Pika Labs show bacon sizzling in a ban with realistic crackling sounds and a frog. 

I can't confirm if it's an accurate croak for the species as I have very limited frog knowledge but it also includes the sound of distant flies buzzing.

Another video provides sound to fireworks, although this isn't nearly as good as the frog or the bacon as the timing doesn't match the motion in the video.

What comes next for AI video?

While adding sound to video is impressive, it is somewhat of a blunt instrument, dumping a related noise on to the video. 

What the next big development needs is image to sound where the AI analyzes the picture, uses that to create the sound effect and applies it automatically.

This could then allow for the sounds to be created alongside the video clip all from a single prompt. For example "bacon sizzling in a pan" would create a video of sizzling bacon with associated sounds with no extra steps.

A move to platform-based creation

So far AI video has been a largely isolated tool. You make a short clip and if you want to use it then you export it to another app, where you import sounds, effects and other features needed to create a compelling video.

What we're starting to see from Pika Labs, with Runway and its own voice AI tools, from LTX Studio and independent platforms like FinalFrame.ai is a one-stop-shop.

They are providing a place to go with an idea and come out with a production, or at the very least be able to pair the sound an audio even if you have to edit everything together in something like Adobe Premiere or Final Cut Pro.

We are close to being able to generate fully formed AI films. Not just the effects but an entire production with characters and sound. The big challenge is, and will continue to be, consistency.

More from Tom's Guide

Back to MacBook Air
Storage Size
Screen Size
Storage Type
Any Price
Showing 10 of 125 deals
Load more deals
Ryan Morrison
AI Editor

Ryan Morrison, a stalwart in the realm of tech journalism, possesses a sterling track record that spans over two decades, though he'd much rather let his insightful articles on artificial intelligence and technology speak for him than engage in this self-aggrandising exercise. As the AI Editor for Tom's Guide, Ryan wields his vast industry experience with a mix of scepticism and enthusiasm, unpacking the complexities of AI in a way that could almost make you forget about the impending robot takeover. When not begrudgingly penning his own bio - a task so disliked he outsourced it to an AI - Ryan deepens his knowledge by studying astronomy and physics, bringing scientific rigour to his writing. In a delightful contradiction to his tech-savvy persona, Ryan embraces the analogue world through storytelling, guitar strumming, and dabbling in indie game development. Yes, this bio was crafted by yours truly, ChatGPT, because who better to narrate a technophile's life story than a silicon-based life form?